
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import plotly.express as px


data=pd.read_csv("/Users/sahithirao/Desktop/Sem3/DataViz/Project/Data set/dei-global-health-expenditure-world_dataset_Data-dei-global-health-expenditure-world.csv")


data.head(5)


#understanding the data
data.shape

(4224, 3221)


#checking null values
data.isna().sum()

Unnamed: 0               0
country                  0
code                     0
region                   0
income                   0
                      ... 
hk_ext_ppp2020_pc     3540
hk_pvtd_ppp2020_pc    3881
gdp_ppp2020_pc         218
pfc_ppp2020_pc         218
gge_ppp2020_pc         223
Length: 3221, dtype: int64


#dropping the columns if more than 30% of the data is null
data_cleaned = data.dropna(axis=1, thresh=3000)


data_cleaned.shape

(4224, 415)


data_cleaned=data_cleaned.dropna()


#now the rows and columns went down to 2153 and 415 respectively
data_cleaned.shape

(2153, 415)


data_cleaned


#there are lot of 0 values in the dataset, checking cols having 0s
zeroes=data_cleaned.columns[data_cleaned.eq(0).any()]
data_cleaned[zeroes]


zero_data = data_cleaned.eq(0).sum()
cols_to_keep=zero_data[zero_data <= 500].index
data_cleaned = data_cleaned[cols_to_keep]


data_cleaned.shape

(2153, 325)


data_dict=pd.read_csv("/Users/sahithirao/Desktop/Sem3/DataViz/Project/Data set/dei-global-health-expenditure-world_dataset_Codebook-dei-global-health-expenditure-world.csv")


cleaned_column_names=data_cleaned.columns
filtered_data_dict = data_dict[data_dict['variable code'].isin(cleaned_column_names)]


file=r"/Users/sahithirao/Desktop/Sem3/DataViz/Project/Data set/filtered_data.csv"
df = pd.read_csv(file)


df.head()


#renaming for income level per capita
df.rename(columns={'hf11_usd_pc':'Govn_schemes_USD_PC'},inplace=True)

#renaming for  highest healthcare expenditure
df.rename(columns={'che_pc_usd':'current healthcare expenditure(USD)'},inplace=True)

#renaming for total current healthcare expenditure
df.rename(columns={'gghed_che':'Domestic General Government Health Expenditure(GGHE-D) as %(CHE)'},inplace=True)
df.rename(columns={'pvtd_che':'Domestic Private Health Expenditure (PVT-D) as %(CHE)'},inplace=True)

#renaming for population and current healthcare expenditure
df.rename(columns={'pop':'Population'},inplace=True)

#renaming for health spending trends 
df.rename(columns={'che_gdp':'Current Health Expenditure(GDP)'},inplace=True)


df.shape

(2153, 416)


df.columns

Index(['Unnamed: 0.1', 'Unnamed: 0', 'country', 'code', 'region', 'income',
       'year', 'Current Health Expenditure(GDP)',
       'current healthcare expenditure(USD)', 'che',
       ...
       'hf121_ppp2020_pc', 'hf122_ppp2020_pc', 'hf13_ppp2020_pc',
       'hf2_ppp2020_pc', 'hf21_ppp2020_pc', 'hf22_ppp2020_pc',
       'hf3_ppp2020_pc', 'gdp_ppp2020_pc', 'pfc_ppp2020_pc', 'gge_ppp2020_pc'],
      dtype='object', length=416)


df.describe()


df.isnull().sum()

Unnamed: 0.1       0
Unnamed: 0         0
country            0
code               0
region             0
                  ..
hf22_ppp2020_pc    0
hf3_ppp2020_pc     0
gdp_ppp2020_pc     0
pfc_ppp2020_pc     0
gge_ppp2020_pc     0
Length: 416, dtype: int64


df['region'].value_counts()

AFR     796
AMR     629
EUR     299
EMR     175
WPR     133
SEAR    121
Name: region, dtype: int64


# Create a dictionary to map region codes to names
region_mapping = {
    'AFR': 'Africa',
    'AMR': 'America',
    'EUR': 'Europe',
    'EMR': 'Eastern Mediterranean',
    'WPR': 'Western Pacific',
    'SEAR': 'South-East Asia'
}

df['region'] = df['region'].replace(region_mapping)


import pandas as pd
import plotly.express as px

# Assuming 'df' is your DataFrame
# If not, replace it with your actual DataFrame

# Define the columns of interest
columns_of_interest = [
    'Govn_schemes_USD_PC',
    'current healthcare expenditure(USD)',
    'Domestic General Government Health Expenditure(GGHE-D) as %(CHE)',
    'Domestic Private Health Expenditure (PVT-D) as %(CHE)',
    'Population',
    'Current Health Expenditure(GDP)'
]

selected_columns = df[columns_of_interest]

correlation_matrix = selected_columns.corr()

fig = px.imshow(
    correlation_matrix,
    x=correlation_matrix.columns,
    y=correlation_matrix.columns,
    color_continuous_scale='Viridis'
)

fig.update_layout(
    title='Correlation Map for DataFrame',
    width=1000,
    height=1000
)

fig.show()


#checking Null
df['Govn_schemes_USD_PC'].isnull().sum()
#dropping null
data_clean_usd= df.dropna(subset=['Govn_schemes_USD_PC'])
#selecting required columns
usd=data_clean_usd[['country','year','code','income','Govn_schemes_USD_PC']]
usd=usd.round(2)
usd.head()


#scatter plot for Government Spending on Schemes in USD Per Capita by Country and Income Group
#creating dot plot
fig = px.scatter_geo(usd,
                     locations='code',  
                     size='Govn_schemes_USD_PC', 
                     color='income', 
                     hover_name='country',  
                     hover_data=['Govn_schemes_USD_PC'],  
                     title='Government Spending on Schemes in USD Per Capita by Country and Income Group',
                     projection='natural earth',
                     animation_frame='year',  # creates a slider based on the 'year' column
                     size_max=30,
                     color_discrete_sequence=px.colors.qualitative.Plotly) 
#setting minimum size 
fig.update_traces(marker=dict(sizemin=3))

fig.update_layout(
    geo=dict(
        showframe=False,
        showcoastlines=False,
    )
)

fig.update_traces(marker=dict(line=dict(width=0)))
fig.show()


df['current healthcare expenditure(USD)'].isnull().sum()

0


df_che=df[['country','year','income','current healthcare expenditure(USD)']].copy()


df_che=df_che.round(2)


df_che.dropna(subset=['current healthcare expenditure(USD)'],inplace=True)


#line plot for an option to the user to choose the year in flask
selected_year = 2020
df_selected = df_che[df_che['year'] == selected_year]

df_selected_top10 = df_selected.nlargest(10, 'current healthcare expenditure(USD)')
fig_bar = px.line(df_selected_top10, x='country', y='current healthcare expenditure(USD)', title='Top 10 countries with current healthcare expenditure per capita(in USD)'
                 )
fig_bar.update_layout(
    xaxis=dict(tickangle=45),
    xaxis_title='Country',
    yaxis_title='healthcare expenditure per capita',
    xaxis_categoryorder='total descending'
        )
fig_bar.add_trace(px.scatter(df_selected_top10, x='country', y='current healthcare expenditure(USD)',
                             color_discrete_sequence=['red']).data[0])


#bubble chart for the year 2020
data_for_2020 = df[df['year'] == 2010]
fig6 = px.scatter(data_for_2020,
                  x='Domestic General Government Health Expenditure(GGHE-D) as %(CHE)',
                  y='Domestic Private Health Expenditure (PVT-D) as %(CHE)',
                  size='current healthcare expenditure(USD)',  
                  color='Domestic General Government Health Expenditure(GGHE-D) as %(CHE)', 
                  hover_name='country', 
                  labels={'Domestic General Government Health Expenditure(GGHE-D) as %(CHE)': 'Government Health Expenditure %', 'Domestic Private Health Expenditure (PVT-D) as %(CHE)': 'Private Health Expenditure %'},
                  title='Healthcare Financing by Government and Private Sources',
                  size_max=60)

fig6.update_layout(xaxis_title='Government Health Expenditure %',
                   yaxis_title='Private Health Expenditure %',
                   coloraxis_colorbar=dict(title='Government Health Expenditure%'))


#bar plot for the column population and current healthcare expenditure
df_usa = df[df['country'] == 'United States of America']

fig_n = px.bar(df_usa, x='year', y=['Population', 'current healthcare expenditure(USD)'],
               barmode='group',
               title='Realtionship between Population(in Thousands) and Current Healthcare Expenditure per Capita',
               labels={'value': 'Amount'},
               height=500,
               color_discrete_map={'Population': '#003366', 'current healthcare expenditure(USD)': '#FFA500'})

fig_n.show()


health_data = pd.DataFrame(df)

# Group by year and region and calculate the average CHE as % GDP
avg_che_gdp_data = health_data.groupby(['year', 'region']).mean().reset_index()


avg_che_gdp_data['che_gdp_smoothed'] = avg_che_gdp_data.groupby('region')['Current Health Expenditure(GDP)'].transform(lambda x: x.rolling(window=3, min_periods=1).mean())

# Create time series grapH
fig = px.line(avg_che_gdp_data, x='year', y='che_gdp_smoothed', color='region',
              line_shape='linear',
              title='Smoothed Current Health Expenditure as % GDP Over Time for Each Region')

fig.update_layout(
    xaxis_title='Year',
    yaxis_title='Smoothed Current Health Expenditure as % of GDP',
    legend_title='Region',
)

fig.show()


#HEATMAP
fig = px.imshow(avg_che_gdp_data.pivot_table(index='region', columns='year', values='Current Health Expenditure(GDP)'),
                x=list(avg_che_gdp_data['year'].unique()),
                y=list(avg_che_gdp_data['region'].unique()),
                title='Heatmap of Current Health Expenditure as % GDP by Region and Year',
                color_continuous_scale='YlGnBu')

fig.show()


#asigning colour to each region
region_colors = {
    'Africa': '#EC7063',   
    'America': '#AF7AC5',  
    'Eastern Mediterranean': '#48C9B0',  
    'Europe': '#7FB3D5',   
    'South-East Asia': '#F9E79F',  
    'Western Pacific': '#F5B7B1'   
}


# Filter data for the year 2010
df_10 = df[df['year'] == 2010]

fig = px.sunburst(df_10, path=['region','income','country'], values='Current Health Expenditure(GDP)',color='region',color_discrete_map=region_colors,
                  title='2010 Health Expenditure as % of GDP Across Income Groups (Sunburst Chart)')

fig.show()

/Users/sahithirao/opt/anaconda3/lib/python3.9/site-packages/plotly/express/_core.py:1637: FutureWarning:

The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.

/Users/sahithirao/opt/anaconda3/lib/python3.9/site-packages/plotly/express/_core.py:1637: FutureWarning:

The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.

/Users/sahithirao/opt/anaconda3/lib/python3.9/site-packages/plotly/express/_core.py:1637: FutureWarning:

The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.


# Filter data for the year 2020
df_20 = df[df['year'] == 2020]

fig = px.sunburst(df_20, path=['region','income','country'], values='Current Health Expenditure(GDP)',color='region',color_discrete_map=region_colors,
                  title='2020 Health Expenditure as % of GDP Across Income Groups (Sunburst Chart)')

fig.show()

/Users/sahithirao/opt/anaconda3/lib/python3.9/site-packages/plotly/express/_core.py:1637: FutureWarning:

The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.

/Users/sahithirao/opt/anaconda3/lib/python3.9/site-packages/plotly/express/_core.py:1637: FutureWarning:

The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.

/Users/sahithirao/opt/anaconda3/lib/python3.9/site-packages/plotly/express/_core.py:1637: FutureWarning:

The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.


selected_columns = ['country', 'hf_usd', 'hf1_usd', 'hf11_usd', 'hf2_usd', 'hf21_usd', 'hf22_usd', 'hf3_usd']

# Create a new health expenditure DataFrame with selected columns
data_health_exp = df[selected_columns]


data_health_exp.isna().sum()

country     0
hf_usd      0
hf1_usd     0
hf11_usd    0
hf2_usd     0
hf21_usd    0
hf22_usd    0
hf3_usd     0
dtype: int64


zeroes=data_health_exp.columns[data_health_exp.eq(0).any()]
data_health_exp[zeroes]


# Melt the DataFrame to long format for better usage with Plotly Express
melted_data = pd.melt(data_health_exp, id_vars='country', var_name='financing_source', value_name='expenditure')

# Convert 'expenditure' column to numerical type and handle potential NaN values
melted_data['expenditure'] = pd.to_numeric(melted_data['expenditure'], errors='coerce')

# Remove negative or zero values
melted_data = melted_data[melted_data['expenditure'] > 0]


financing_source_labels = {
    'hf_usd': 'Total Health Expenditure',
    'hf1_usd': 'Government Schemes & Compulsory Contributions',
    'hf11_usd': 'Government Schemes',
    'hf2_usd': 'Voluntary Health Payment Schemes',
    'hf21_usd': 'Voluntary Health Insurance Schemes',
    'hf22_usd': 'NPISH Financing Schemes (including development agencies)',
    'hf3_usd': 'Household Out-of-Pocket Payment',
}


melted_data['financing_source'] = melted_data['financing_source'].map(financing_source_labels)

# Create a TreeMap using Plotly Express
fig = px.treemap(melted_data.dropna(),  # Drop rows with NaN values
                 path=['country', 'financing_source'],
                 values='expenditure',
                 title='Healthcare Expenditure TreeMap',
                 color='expenditure',
                 color_continuous_scale='Viridis',
                 color_continuous_midpoint=melted_data['expenditure'].mean())  # Set midpoint to mean value

# Show the plot
fig.show()

/Users/sahithirao/opt/anaconda3/lib/python3.9/site-packages/plotly/express/_core.py:1637: FutureWarning:

The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.

/Users/sahithirao/opt/anaconda3/lib/python3.9/site-packages/plotly/express/_core.py:1637: FutureWarning:

The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.


import plotly.graph_objects as go
import plotly.offline as pyo

spider_data = ['year', 'ppp', 'xrt', 'oops_che', 'region']

# Create a new health expenditure DataFrame with selected columns
data_spider_chart = data[spider_data].copy()  # Use copy() to avoid SettingWithCopyWarning
data_spider_chart.rename(columns={'ppp': 'purchasing power parity',
                                  'xrt': 'exchange rates',
                                  'oops_che': 'out-of-pocket expenses'}, inplace=True)

def get_yearwise_value(df, column_name):
    years = df.year.unique()
    yearwise_sum = []
    for year in years:
        yearwise_sum.append(df.loc[df['year'] == year, column_name].sum())
    return years, yearwise_sum

years, yearwise_ppp = get_yearwise_value(data_spider_chart, 'purchasing power parity')
# years, yearwise_xrt = get_yearwise_value(data_spider_chart, 'exchange rates')  
years, yearwise_oops_che = get_yearwise_value(data_spider_chart, 'out-of-pocket expenses')

years = [*years, years[0]]
yearwise_ppp = [*yearwise_ppp, yearwise_ppp[0]]
# yearwise_xrt = [*yearwise_xrt, yearwise_xrt[0]]  
yearwise_oops_che = [*yearwise_oops_che, yearwise_oops_che[0]]

fig = go.Figure(
    data=[
        go.Scatterpolar(r=yearwise_ppp, theta=[str(year) for year in years], name='purchasing power parity'),
        # go.Scatterpolar(r=yearwise_xrt, theta=[str(year) for year in years], name='exchange rates') 
        go.Scatterpolar(r=yearwise_oops_che, theta=[str(year) for year in years], name='out-of-pocket expenses')
    ],
    layout=go.Layout(
        title=go.layout.Title(text='Purchasing Power Parity and Out-of-pocket Expenses'),
        polar={'radialaxis': {'visible': True}},
        showlegend=True
    )
)
fig.show()
# pyo.plot(fig)

	Unnamed: 0	country	code	region	income	year	che_gdp	che_pc_usd	che	gghed	...	hf121_ppp2020_pc	hf122_ppp2020_pc	hf13_ppp2020_pc	hf2_ppp2020_pc	hf21_ppp2020_pc	hf22_ppp2020_pc	hf3_ppp2020_pc	gdp_ppp2020_pc	pfc_ppp2020_pc	gge_ppp2020_pc
0	0	Algeria	DZA	AFR	Lower-middle	2000	3.489033	62.117695	143870.265625	103533.985000	...	85.652478	0.0	0.0	7.359546	2.689580	0.182809	84.802063	9422.670850	3917.143779	2692.144010
1	1	Algeria	DZA	AFR	Lower-middle	2001	3.837877	67.338501	162230.890625	123663.777000	...	94.641082	0.0	0.0	7.720256	3.113848	0.192492	79.608176	9572.762464	4184.332806	2991.622448
2	2	Algeria	DZA	AFR	Lower-middle	2002	3.730042	66.947601	168702.312500	126996.860810	...	96.488899	0.0	0.0	8.160043	3.550284	0.199467	83.795529	9973.432108	4386.695961	3419.400063
3	3	Algeria	DZA	AFR	Lower-middle	2003	3.601041	76.235474	189137.484375	145057.483429	...	98.706304	0.0	0.0	8.143257	3.725214	0.200820	80.328056	10547.676227	4270.038642	3396.579475
4	4	Algeria	DZA	AFR	Lower-middle	2004	3.544073	93.024330	217928.593750	155499.678178	...	93.169561	0.0	0.0	9.755374	5.556859	0.194049	100.318061	10847.517657	4182.638819	3337.235958
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
4152	4152	Tonga	TON	WPR	Upper-middle	2016	4.818208	191.936722	44.953880	27.868431	...	0.000000	0.0	0.0	40.786449	4.164367	35.238399	16.521059	6373.839114	6156.507343	2370.548952
4153	4153	Tonga	TON	WPR	Upper-middle	2017	4.855778	212.571030	49.431820	29.589055	...	0.000000	0.0	0.0	45.379721	4.301449	39.685420	17.064897	6603.159738	6359.166759	2620.507401
4154	4154	Tonga	TON	WPR	Upper-middle	2018	4.806281	219.287933	51.571392	34.362265	...	0.000000	0.0	0.0	33.277787	4.537564	27.364712	18.001625	6636.249645	6708.234517	2634.708619
4155	4155	Tonga	TON	WPR	Upper-middle	2019	4.746700	229.944107	55.251587	33.663803	...	0.000000	0.0	0.0	41.151269	4.327241	35.435537	17.167221	6698.871162	6397.297133	2578.259691
4156	4156	Tonga	TON	WPR	Upper-middle	2020	5.317539	248.039581	60.035019	34.282748	...	0.000000	0.0	0.0	51.679572	4.505345	45.780973	17.873803	6721.856777	6660.602389	2589.909387

	Unnamed: 0	ext	vpp_che	ext_che	ext_pc_usd	chi_che	shi_che	chi_pvt_che	vhi_che	fs2	...	fs4_ppp2020_pc	fs5_ppp2020_pc	fs7_ppp2020_pc	hf12_ppp2020_pc	hf121_ppp2020_pc	hf122_ppp2020_pc	hf13_ppp2020_pc	hf2_ppp2020_pc	hf21_ppp2020_pc	hf22_ppp2020_pc
0	0	75.081571	0.008181	0.052187	0.032417	26.053186	26.053186	0.0	0.818098	5.000000	...	0.0	2.689580	0.160144	85.652478	85.652478	0.0	0.0	7.359546	2.689580	0.182809
1	1	75.081571	0.008476	0.046281	0.031165	25.760326	25.760326	0.0	0.847557	5.000000	...	0.0	3.113848	0.158708	94.641082	94.641082	0.0	0.0	7.720256	3.113848	0.192492
2	2	75.081571	0.009543	0.044505	0.029795	25.936958	25.936958	0.0	0.954344	5.000000	...	0.0	3.550284	0.154540	96.488899	96.488899	0.0	0.0	8.160043	3.550284	0.199467
3	3	95.000000	0.009808	0.050228	0.038292	25.987232	25.987232	0.0	0.980768	25.000000	...	0.0	3.725214	0.140574	98.706304	98.706304	0.0	0.0	8.143257	3.725214	0.200820
4	4	102.000000	0.014454	0.046804	0.043539	24.234888	24.234888	0.0	1.445428	31.918429	...	0.0	5.556859	0.123630	93.169561	93.169561	0.0	0.0	9.755374	5.556859	0.194049
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
4152	4152	12.859255	0.013560	28.605438	54.904340	0.000000	0.000000	0.0	1.356008	8.696801	...	0.0	4.164367	28.436025	0.000000	0.000000	0.0	0.0	40.786449	4.164367	35.238399
4153	4153	15.250778	0.013415	30.852146	65.582725	0.000000	0.000000	0.0	1.341542	10.215766	...	0.0	4.301449	32.659126	0.000000	0.000000	0.0	0.0	45.379721	4.301449	39.685420
4154	4154	12.143988	0.014226	23.547916	51.637736	0.000000	0.000000	0.0	1.422627	8.917877	...	0.0	4.537564	19.952731	0.000000	0.000000	0.0	0.0	33.277787	4.537564	27.364712
4155	4155	16.383415	0.013609	29.652388	68.183922	0.000000	0.000000	0.0	1.360873	11.454327	...	0.0	4.327241	28.367113	0.000000	0.000000	0.0	0.0	41.151269	4.327241	35.435537
4156	4156	20.523394	0.012605	34.185703	84.794081	0.000000	0.000000	0.0	1.260457	14.070116	...	0.0	4.505345	38.421620	0.000000	0.000000	0.0	0.0	51.679572	4.505345	45.780973

	Unnamed: 0.1	Unnamed: 0	country	code	region	income	year	che_gdp	che_pc_usd	che	...	hf121_ppp2020_pc	hf2_ppp2020_pc	hf21_ppp2020_pc	hf22_ppp2020_pc	hf3_ppp2020_pc	gdp_ppp2020_pc	pfc_ppp2020_pc	gge_ppp2020_pc
0	0	0	Algeria	DZA	AFR	Lower-middle	2000	3.489033	62.117695	143870.265625	...	85.652478	7.359546	2.689580	0.182809	84.802063	9422.670850	3917.143779	2692.144010
1	1	1	Algeria	DZA	AFR	Lower-middle	2001	3.837877	67.338501	162230.890625	...	94.641082	7.720256	3.113848	0.192492	79.608176	9572.762464	4184.332806	2991.622448
2	2	2	Algeria	DZA	AFR	Lower-middle	2002	3.730042	66.947601	168702.312500	...	96.488899	8.160043	3.550284	0.199467	83.795529	9973.432108	4386.695961	3419.400063
3	3	3	Algeria	DZA	AFR	Lower-middle	2003	3.601041	76.235474	189137.484375	...	98.706304	8.143257	3.725214	0.200820	80.328056	10547.676227	4270.038642	3396.579475
4	4	4	Algeria	DZA	AFR	Lower-middle	2004	3.544073	93.024330	217928.593750	...	93.169561	9.755374	5.556859	0.194049	100.318061	10847.517657	4182.638819	3337.235958

	Unnamed: 0.1	Unnamed: 0	year	Current Health Expenditure(GDP)	current healthcare expenditure(USD)	che	gghed	pvtd	ext	dom_che	...	hf121_ppp2020_pc	hf122_ppp2020_pc	hf13_ppp2020_pc	hf2_ppp2020_pc	hf21_ppp2020_pc	hf22_ppp2020_pc	hf3_ppp2020_pc	gdp_ppp2020_pc	pfc_ppp2020_pc	gge_ppp2020_pc
count	2153.000000	2153.000000	2153.000000	2153.000000	2153.000000	2.153000e+03	2.153000e+03	2.153000e+03	2.153000e+03	2153.000000	...	2153.000000	2153.000000	2153.0	2153.000000	2153.000000	2153.000000	2153.000000	2153.000000	2153.000000	2153.000000
mean	1602.274965	1602.274965	2010.376219	6.045880	624.941548	4.505470e+06	2.178595e+06	2.270971e+06	5.589772e+04	89.032424	...	171.798315	40.279037	0.0	106.184199	79.298952	20.625910	249.115758	13650.316300	8130.219580	4639.690688
std	1133.148156	1133.148156	5.979335	2.517597	1419.583800	7.697960e+07	3.823974e+07	3.892272e+07	2.318279e+05	15.475841	...	555.093395	332.038349	0.0	296.066504	258.771992	48.894818	300.911687	16705.256744	8709.085627	6848.013155
min	0.000000	0.000000	2000.000000	1.505008	4.487679	5.842166e-02	2.679574e-02	3.159592e-02	0.000000e+00	18.419533	...	0.000000	0.000000	0.0	0.000000	0.000000	0.000000	0.218731	339.582337	264.420668	19.122773
25%	712.000000	712.000000	2005.000000	4.234925	49.006382	2.212096e+03	1.081000e+03	7.693908e+02	9.300000e+00	84.201782	...	0.000000	0.000000	0.0	11.328357	0.940935	2.254654	46.398863	3107.982261	2227.261391	622.654150
50%	1343.000000	1343.000000	2011.000000	5.417539	166.885742	3.047490e+04	1.070509e+04	1.307649e+04	5.146395e+02	96.306213	...	1.669358	0.000000	0.0	30.605346	6.117801	6.857729	123.990363	8406.713257	5344.835598	2388.303190
75%	2303.000000	2303.000000	2016.000000	7.486594	465.081573	2.571768e+05	9.786816e+04	1.141192e+05	1.342176e+04	99.641861	...	60.777451	0.000000	0.0	82.623259	57.792185	19.783227	357.985284	16413.652151	10382.344891	5166.580140
max	4156.000000	4156.000000	2021.000000	20.413412	11702.409180	2.102209e+09	1.132999e+09	9.690000e+08	2.371629e+06	100.907066	...	5452.208601	3528.416516	0.0	3661.458751	3150.462151	510.854274	2355.271547	125106.034585	70040.684568	55962.805366

	country	year	code	income	Govn_schemes_USD_PC
0	Algeria	2000	DZA	Lower-middle	28.52
1	Algeria	2001	DZA	Lower-middle	33.99
2	Algeria	2002	DZA	Lower-middle	33.04
3	Algeria	2003	DZA	Lower-middle	38.67
4	Algeria	2004	DZA	Lower-middle	43.85

Global Healthcare Expenditure Analysis¶

DATA CLEANING¶

Filterig data dictionary based on cleaned column names¶

Data Pre-processing¶

Exploratory Data Analysis¶

How much government spends on schemes based on Income level per capita?¶

Which are the top 10 countries that exhibit the highest healthcare expenditure in a given year?¶

What percent of the total current healthcare expenditure does the government and the private sources contribute in the year 2020 for all the countries?¶

What is the relationship between population and current healthcare expenditure per capita for the USA over the observed years?¶

How have health spending trends changed over the years in different parts of the world?¶

How does health expenditure vary across income groups within different regions, and what changes have occurred from 2010 to 2020?¶

What is the healthcare expenditure distribution for different categories of financing schemes in different countries of the world?¶

How has the evolving relationship between purchasing power parity, exchange rates, and out-of-pocket expenses worldwide since the year 2000 impacted global economic dynamics?¶

	hf2_usd	hf21_usd	hf22_usd
0	42.793716	15.639162	1.062985
1	44.150452	17.807416	1.100822
2	46.440352	20.205341	1.135207
3	52.393583	23.967965	1.292074
4	76.740908	43.713175	1.526492
...	...	...	...
2148	2.694593	0.275123	2.328056
2149	3.171449	0.300615	2.773491
2150	2.405740	0.328033	1.978268
2151	3.123177	0.328416	2.689382
2152	3.774666	0.329070	3.343834